Research map / Label-efficient and robust learning / Recognition and long-tail
Meta-Mining Discriminative Samples for Kinship Verification
Wanhua Li, Shiwei Wang, Jiwen Lu, Jianjiang Feng, Jie Zhou
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply DSMM meta-mining instead of the strongest listed baseline | KinFaceW-I verification · KinFaceW-I | mean accuracy (%): +3.7% | Improved |
| Apply DSMM meta-mining instead of the strongest listed baseline | KinFaceW-II verification · KinFaceW-II | mean accuracy (%): +4.6% | Improved |
| Apply DSMM meta-mining instead of the strongest listed baseline | TSKinFace verification · TSKinFace | mean accuracy (%): +4.9% | Improved |
| Apply DSMM meta-mining instead of the strongest listed baseline | Cornell KinFace verification · Cornell KinFace | mean accuracy (%): +8.8% | Improved |
| Add the DSMM meta-miner to the relation model (ablation) | KinFaceW-I relation model · KinFaceW-I | mean accuracy (%): 78.1 -> 82.4 | Improved |
| Add the DSMM meta-miner to the relation model (ablation) | KinFaceW-II relation model · KinFaceW-II | mean accuracy (%): 90.4 -> 93.0 | Improved |
| Use focal loss instead of meta-learned sample weighting (ablation) | KinFaceW-I and KinFaceW-II training · KinFaceW-I; KinFaceW-II | mean accuracy (%): 80.9 -> 74.6; 91.8 -> 80.5 | Hurt |
| Use unbalanced batches with fixed negative weights instead of balanced-batch resampling (ablation) | KinFaceW-I and KinFaceW-II training · KinFaceW-I; KinFaceW-II | mean accuracy (%): 80.9 -> 80.9; 91.8 -> 92.5 | Mixed |
| Set C to 4 rather than C=1, 2, or 8 (ablation) | DSMM training · KinFaceW-I | mean accuracy (%): 81.8; 80.6; 82.4; 79.8 | Mixed |
| Set C to 2 rather than C=1, 3, or 4 (ablation) | DSMM training · KinFaceW-II | mean accuracy (%): 92.5; 93.0; 91.3; 90.5 | Mixed |
Closest papers by meaning
- Kinship Identification through Joint Learning using Kinship Verification Ensembles (ECCV 2020 · similarity 0.90)
- Facial Kinship Verification: A Comprehensive Review and Outlook (IJCV 2022 · similarity 0.88)
- Cross-Generation Kinship Verification with Sparse Discriminative Metric (TPAMI 2018 · similarity 0.88)
- Visual Kinship Recognition of Families in the Wild (TPAMI 2018 · similarity 0.88)
- Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making (TPAMI 2021 · similarity 0.88)
- Unsupervised Model Tree Heritage Recovery (ICLR 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
